Registration without Correspondences.

摘要

In this paper, we present a method for registering images of complex 3-D surfaces that does not require explicit correspondences between features across the images. Our method relies on the use of a full 3-D model of the surface to adjust the position and orientation of the camera by minimizing an objective function based on the projections of the images onto the model. This approach constrains the camera parameters strongly enough so that the models do not need, initially, to be accurate to yield good results. When registration has been achieved, the models can be refined and the fine details recovered. We use the 3-D surface models to adjust not only the surface's shape but also the position and orientation of the cameras by minimizing an objective function based on the projections of the model into the images. The method presented here complements our approach, described in previous publications, to the recovery of 3-D surface models from multiple images whose camera parameters are known. Our method is applicable to the calibration of stereo imagery, the precise registration of new images of a scene and the tracking of deformable objects. It can therefore lead to important applications in fields such as augmented reality in a medical context or data compression for transmission purposes. We demonstrate its applicability by using both synthetic images and real images of faces and of terrain.